Qwen3 235B 2507 vs Ministral 3 8B (Reasoning)

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Qwen3 235B 2507 finishes one point ahead overall, 37 to 36. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.

Qwen3 235B 2507's sharpest advantage is in multimodal & grounded, where it averages 41.6 against 33.4. The single biggest benchmark swing on the page is MMMU-Pro, 38 to 28. Ministral 3 8B (Reasoning) does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Ministral 3 8B (Reasoning) is the reasoning model in the pair, while Qwen3 235B 2507 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

Quick Verdict

Pick Qwen3 235B 2507 if you want the stronger benchmark profile. Ministral 3 8B (Reasoning) only becomes the better choice if agentic is the priority or you want the stronger reasoning-first profile.

Agentic

Ministral 3 8B (Reasoning)

Qwen3 235B 2507

33.7

Ministral 3 8B (Reasoning)

38.5

33
Terminal-Bench 2.0
39
40
BrowseComp
41
30
OSWorld-Verified
36

Coding

Ministral 3 8B (Reasoning)

Qwen3 235B 2507

14.6

Ministral 3 8B (Reasoning)

15.2

31
HumanEval
24
15
SWE-bench Verified
17
10
LiveCodeBench
16
19
SWE-bench Pro
14

Multimodal & Grounded

Qwen3 235B 2507

Qwen3 235B 2507

41.6

Ministral 3 8B (Reasoning)

33.4

38
MMMU-Pro
28
46
OfficeQA Pro
40

Reasoning

Qwen3 235B 2507

Qwen3 235B 2507

45.6

Ministral 3 8B (Reasoning)

42.1

37
SimpleQA
32
35
MuSR
33
60
BBH
70
52
LongBench v2
44
52
MRCRv2
47

Knowledge

Qwen3 235B 2507

Qwen3 235B 2507

31.9

Ministral 3 8B (Reasoning)

30

39
MMLU
30
38
GPQA
29
36
SuperGPQA
27
34
OpenBookQA
25
51
MMLU-Pro
54
1
HLE
5
39
FrontierScience
34

Instruction Following

Ministral 3 8B (Reasoning)

Qwen3 235B 2507

69

Ministral 3 8B (Reasoning)

70

69
IFEval
70

Multilingual

Ministral 3 8B (Reasoning)

Qwen3 235B 2507

60.4

Ministral 3 8B (Reasoning)

61.7

63
MGSM
63
59
MMLU-ProX
61

Mathematics

Ministral 3 8B (Reasoning)

Qwen3 235B 2507

46.6

Ministral 3 8B (Reasoning)

47.8

39
AIME 2023
33
41
AIME 2024
35
40
AIME 2025
34
35
HMMT Feb 2023
29
37
HMMT Feb 2024
31
36
HMMT Feb 2025
30
38
BRUMO 2025
32
57
MATH-500
67

Frequently Asked Questions

Which is better, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Qwen3 235B 2507 is ahead overall, 37 to 36. The biggest single separator in this matchup is MMMU-Pro, where the scores are 38 and 28.

Which is better for knowledge tasks, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Qwen3 235B 2507 has the edge for knowledge tasks in this comparison, averaging 31.9 versus 30. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Ministral 3 8B (Reasoning) has the edge for coding in this comparison, averaging 15.2 versus 14.6. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Ministral 3 8B (Reasoning) has the edge for math in this comparison, averaging 47.8 versus 46.6. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Qwen3 235B 2507 has the edge for reasoning in this comparison, averaging 45.6 versus 42.1. Inside this category, BBH is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Ministral 3 8B (Reasoning) has the edge for agentic tasks in this comparison, averaging 38.5 versus 33.7. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Qwen3 235B 2507 has the edge for multimodal and grounded tasks in this comparison, averaging 41.6 versus 33.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Ministral 3 8B (Reasoning) has the edge for instruction following in this comparison, averaging 70 versus 69. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Qwen3 235B 2507 or Ministral 3 8B (Reasoning)?

Ministral 3 8B (Reasoning) has the edge for multilingual tasks in this comparison, averaging 61.7 versus 60.4. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.